Computer Graphics
TU Braunschweig

RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications


RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications

In this research work, we present our open-source Geant4-based Monte-Carlo simulation application, called RadField3D, for generating threedimensional radiation field datasets for dosimetry. Accompanying, we introduce a fast, machine-interpretable data format with a Python API for easy integration into neural network research, that we call RadFiled3D. Both developments are intended to be used to research alternative radiation simulation methods using deep learning.


Author(s):Felix Lehner, Pasquale Lombardo, Susana Castillo, Oliver Hupe, Marcus Magnor
Published:May 2025
Type:Article
Journal:Journal of Radiological Protection
DOI:10.1088/1361-6498/add53d
Project(s): Development of a real-time ready photon radiation simulation method 

BibTex PDF arXiv Code Code Link 



@article{lehner2024radfield3d,
  title = {RadField3D: A Data Generator and Data Format for Deep Learning in Radiation-Protection Dosimetry for Medical Applications},
  author = {Lehner, Felix and Lombardo, Pasquale and Castillo, Susana  and Hupe, Oliver and Magnor, Marcus},
  journal = {Journal of Radiological Protection},
  doi = {10.1088/1361-6498/add53d},
  month = {May},
  year = {2025}
}

Authors